sklearn多分类问题中的混淆矩阵

多分类问题中的混淆矩阵

import numpy as np
import matplotlib.pyplot as plt

from sklearn import datasets

digits = datasets.load_digits()
X = digits.data
y = digits.target

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.8, random_state=666)

from sklearn.linear_model import LogisticRegression

log_reg = LogisticRegression()
log_reg.fit(X_train, y_train)
log_reg.score(X_test, y_test)

0.93115438108484

y_predict = log_reg.predict(X_test)

from sklearn.metrics import precision_score

precision_score(y_test, y_predict)

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-6-ae107c9e86ef> in <module>()
      1 from sklearn.metrics import precision_score
      2 
----> 3 precision_score(y_test, y_predict)


~\Anaconda3\lib\site-packages\sklearn\metrics\classification.py in precision_score(y_true, y_pred, labels, pos_label, average, sample_weight)
   1259                                                  average=average,
   1260                                                  warn_for=('precision',),
-> 1261                                                  sample_weight=sample_weight)
   1262     return p
   1263 


~\Anaconda3\lib\site-packages\sklearn\metrics\classification.py in precision_recall_fscore_support(y_true, y_pred, beta, labels, pos_label, average, warn_for, sample_weight)
   1038         else:
   1039             raise ValueError("Target is %s but average='binary'. Please "
-> 1040                              "choose another average setting." % y_type)
   1041     elif pos_label not in (None, 1):
   1042         warnings.warn("Note that pos_label (set to %r) is ignored when "


ValueError: Target is multiclass but average='binary'. Please choose another average setting.

precision_score(y_test, y_predict, average="micro")

0.93115438108484

from sklearn.metrics import confusion_matrix

confusion_matrix(y_test, y_predict)

array([[147,   0,   1,   0,   0,   1,   0,   0,   0,   0],
       [  0, 123,   1,   2,   0,   0,   0,   3,   4,  10],
       [  0,   0, 134,   1,   0,   0,   0,   0,   1,   0],
       [  0,   0,   0, 138,   0,   5,   0,   1,   5,   0],
       [  2,   5,   0,   0, 139,   0,   0,   3,   0,   1],
       [  1,   3,   1,   0,   0, 146,   0,   0,   1,   0],
       [  0,   2,   0,   0,   0,   1, 131,   0,   2,   0],
       [  0,   0,   0,   1,   0,   0,   0, 132,   1,   2],
       [  1,   9,   2,   3,   2,   4,   0,   0, 115,   4],
       [  0,   1,   0,   5,   0,   3,   0,   2,   2, 134]], dtype=int64)

cfm = confusion_matrix(y_test, y_predict)
plt.matshow(cfm, cmap=plt.cm.gray)
plt.show()

row_sums = np.sum(cfm, axis=1)

err_matrix = cfm / row_sums
np.fill_diagonal(err_matrix, 0)

plt.matshow(err_matrix, cmap=plt.cm.gray)
plt.show()

np.fill_diagonal(cfm, 0)
plt.matshow(cfm, cmap=plt.cm.gray)
plt.show()